Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Last update: Dec 29, 2022

Related tags

Deep Learning wechsel

Overview

WECHSEL

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

arXiv: https://arxiv.org/abs/2112.06598

Models from the paper are available on the HuggingFace Hub:

Installation

We distribute a Python Package via PyPI:

pip install wechsel

Alternatively, clone the repository, install requirements.txt and run the code in wechsel/.

Example usage

Transferring English roberta-base to Swahili:

import torch
from transformers import AutoModel, AutoTokenizer
from datasets import load_dataset
from wechsel import WECHSEL, load_embeddings

source_tokenizer = AutoTokenizer.from_pretrained("roberta-base")
model = AutoModel.from_pretrained("roberta-base")

target_tokenizer = source_tokenizer.train_new_from_iterator(
    load_dataset("oscar", "unshuffled_deduplicated_sw", split="train")["text"],
    vocab_size=len(source_tokenizer)
)

wechsel = WECHSEL(
    load_embeddings("en"),
    load_embeddings("sw"),
    bilingual_dictionary="swahili"
)

target_embeddings, info = wechsel.apply(
    source_tokenizer,
    target_tokenizer,
    model.get_input_embeddings().weight.detach().numpy(),
)

model.get_input_embeddings().weight.data = torch.from_numpy(target_embeddings)

# use `model` and `target_tokenizer` to continue training in Swahili!

Bilingual dictionaries

We distribute 3276 bilingual dictionaries from English to other languages for use with WECHSEL in dicts/.

Citation

Please cite WECHSEL as

@misc{minixhofer2021wechsel,
      title={WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models}, 
      author={Benjamin Minixhofer and Fabian Paischer and Navid Rekabsaz},
      year={2021},
      eprint={2112.06598},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Related tags

Overview

WECHSEL

Installation

Example usage

Bilingual dictionaries

Citation

Owner

Institute of Computational Perception

This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

Model-based Reinforcement Learning Improves Autonomous Racing Performance

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Reinforcement Learning for finance

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

JupyterLite demo deployed to GitHub Pages 🚀

Deep Learning for Natural Language Processing SS 2021 (TU Darmstadt)

Code for paper "Document-Level Argument Extraction by Conditional Generation". NAACL 21'

This repository accompanies the ACM TOIS paper "What can I cook with these ingredients?" - Understanding cooking-related information needs in conversational search

A programming language written with python

A copy of Ares that costs 30 fucking dollars.

MoveNetを用いたPythonでの姿勢推定のデモ

Pyramid addon for OpenAPI3 validation of requests and responses.

🎯 A comprehensive gradient-free optimization framework written in Python

LSTM-VAE Implementation and Relevant Evaluations

Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator

The official implementation of CircleNet: Anchor-free Detection with Circle Representation, MICCAI 2030

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

Fine-tune pretrained Convolutional Neural Networks with PyTorch